Open Access

ARTICLE

Deep-Net: Fine-Tuned Deep Neural Network Multi-Features Fusion for Brain Tumor Recognition

by Muhammad Attique Khan^1,2, Reham R. Mostafa³, Yu-Dong Zhang², Jamel Baili⁴, Majed Alhaisoni⁵, Usman Tariq⁶, Junaid Ali Khan¹, Ye Jin Kim⁷, Jaehyuk Cha^7,*

1 Department of Computer Science, HITEC University, Taxila, 47080, Pakistan
2 Department of Informatics, University of Leicester, Leicester, UK
3 Information Systems Department, Faculty of Computers and Information Sciences, Mansoura University, Mansoura, Egypt
4 Department of Computer Engineering, College of Computer Science, King Khalid University, Abha, 61413, Saudi Arabia
5 Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, 11671, Saudi Arabia
6 Management Information System Department, College of Business Administration, Prince Sattam Bin Abdulaziz University, Al-Kharj, 16278, Saudi Arabia
7 Department of Computer Science, Hanyang University, Seoul, 04763, Korea

* Corresponding Author: Jaehyuk Cha. Email:

(This article belongs to the Special Issue: Cancer Diagnosis using Deep Learning, Federated Learning, and Features Optimization Techniques)

Computers, Materials & Continua 2023, 76(3), 3029-3047. https://doi.org/10.32604/cmc.2023.038838

Received 30 December 2022; Accepted 23 May 2023; Issue published 08 October 2023

Abstract

Manual diagnosis of brain tumors using magnetic resonance images (MRI) is a hectic process and time-consuming. Also, it always requires an expert person for the diagnosis. Therefore, many computer-controlled methods for diagnosing and classifying brain tumors have been introduced in the literature. This paper proposes a novel multimodal brain tumor classification framework based on two-way deep learning feature extraction and a hybrid feature optimization algorithm. NasNet-Mobile, a pre-trained deep learning model, has been fine-tuned and two-way trained on original and enhanced MRI images. The haze-convolutional neural network (haze-CNN) approach is developed and employed on the original images for contrast enhancement. Next, transfer learning (TL) is utilized for training two-way fine-tuned models and extracting feature vectors from the global average pooling layer. Then, using a multiset canonical correlation analysis (CCA) method, features of both deep learning models are fused into a single feature matrix—this technique aims to enhance the information in terms of features for better classification. Although the information was increased, computational time also jumped. This issue is resolved using a hybrid feature optimization algorithm that chooses the best classification features. The experiments were done on two publicly available datasets—BraTs2018 and BraTs2019—and yielded accuracy rates of 94.8% and 95.7%, respectively. The proposed method is compared with several recent studies and outperformed in accuracy. In addition, we analyze the performance of each middle step of the proposed approach and find the selection technique strengthens the proposed framework.

---

Keywords

---